Convert JPG to text

Turn JPEG photos and scans into plain text files, one per image, without uploading them.

Convert JPG images to text in your browser. Batch OCR for JPEG photos and scans, copy the text or save .txt files. It is free, needs no account and adds no watermark, and your files are not uploaded: everything runs in your browser on your device. The first run downloads the text reader (about 4 MB) and the WebAssembly engine that runs it to your browser, and after that the tool works offline.

Drop JPG images to convert to textor click to choose files. Batches welcome.
    Details

    Reads printed English text. The first run downloads the text reader and its WebAssembly engine (about 4 MB) from this site; after that it works offline.

    Working…

    Done

    Free, no ads. Support StayPut

    Your files are processed on this device and never sent to a server. Reload the page to clear everything from memory.

    JPG is what cameras, phones and most scanners save, so it is usually the format a page of text arrives in. This page reads each JPG and gives you the text inside it, on screen to copy and as a .txt file with the same name as the image.

    Drop a folder of scanned pages and they are read one after another, then Download all saves every text file in one zip. The work happens in your browser, so a stack of scanned contracts, invoices or old letters never leaves your computer.

    JPEG compression blurs fine detail, which can trip up OCR on small print. If you are scanning, save at 300 dpi and a high quality setting, and the text will come out cleaner.

    Phone cameras save JPGs that are often 4000 px or more across. Anything over 5000 px on its long side is scaled down before reading, and anything under 1200 px is doubled, so you do not need to resize first. What you do need to fix is rotation: text lying on its side is not turned upright for you and comes out as nonsense. Turn sideways photos with Rotate & flip image, then read them here.

    Each result shows a word count, and a note saying low confidence: check it when the reader was unsure of many words. That usually points to a blurry photo, heavy JPEG compression or a busy background. Scanning again at a higher quality setting, or photographing the page flat in daylight, fixes most of these. A JPG that has been forwarded through a chat app a few times has usually been recompressed each time, so ask for the original if you can.

    How it works

    1. Drop one or more JPG files, or tap to pick them.
    2. Choose line breaks as in the image, or joined into paragraphs.
    3. Read text. Copy each result, or download the .txt files, several as one zip.

    In your browser, not on a server

    Your browser decodes the image (libheif or the Squoosh decoders step in for HEIC, AVIF and JPEG XL), enlarges small screenshots so letters are big enough to read, and hands the pixels to Tesseract, the open-source OCR engine first built at HP and later developed by Google, compiled to WebAssembly by tesseract.js (Apache-2.0). Its neural network model for English is served by this site and loaded the first time you run it. The text is recognised line by line inside a worker in your tab.

    Compared with upload-based tools: The pictures people want text from are often private: a letter, a receipt, a bank statement, a prescription, a screenshot of a conversation. Online OCR sites upload the image to their server to read it and keep it for hours, and several limit free use or ask for an account. Here the image never leaves your device, and after your first run the page keeps working with Wi-Fi off.

    Verify it yourself. Give the page a short while after your first run to save itself for offline use, then turn off Wi-Fi or switch to airplane mode and run the tool again. Or open your browser's developer tools (F12, or Cmd-Option-I on a Mac), pick the Network tab, and watch it while you convert. The panel above does the same count for you.

    Questions

    Can I get a Word document instead of text?

    Yes. Image to Word reads the same way and saves one .docx with each image on its own page. Only the text comes across, not the layout.

    What resolution works best?

    Text where a capital letter is at least 20 pixels tall reads best. A full page scanned at 300 dpi, or a phone photo of one page, is plenty. Very small images are enlarged automatically before reading.

    Can I convert a multi-page scan?

    Drop all the pages at once. Each JPG becomes its own .txt file; copy them in order to rebuild the document.

    What does “low confidence: check it” mean?

    The reader scores how sure it is of each word. When the average is low, the result is marked so you know to read it through before you rely on it. The text is still there to copy. Expect mistakes in numbers, names and small print, and compare them with the JPG.

    Do the text files keep the JPG names?

    Yes. scan-003.jpg becomes scan-003.txt, so a folder of numbered scans stays in order. Download all puts every .txt in one zip. Keeping the JPGs named in page order before you drop them makes it easy to join the text back into one document afterwards.

    My photo is sideways. Can it still be read?

    Not reliably. The reader expects lines of text running left to right and does not detect a page turned 90 degrees. Rotate the JPG first with Rotate & flip image, which does it on your device too, then drop the upright copy here.

    Is the file uploaded anywhere?

    No. There is no server in this process. The page is a static file and the work is done by code running inside your browser tab. Give the page a short while after your first run to save itself for offline use; then you can turn off Wi-Fi and it still works.

    More image tools

    Other conversions

    Guides